Kimi K3
GAMoonshot's flagship model, added to the catalog 2026-09-02 — it was missing entirely, which nothing here could see because no instrument reads Moonshot. Official description: "Kimi's most capable model to date, with 2.8 trillion parameters, native visual understanding, and a 1M-token context window", for long-horizon coding and end-to-end knowledge work. Always reasons; reasoning effort is configurable via the top-level reasoning_effort field (low / high / max, default max). Supports automatic context caching, tool calls, JSON mode, structured output, partial mode and web search; K3 adds tool_choice constraints and dynamically loaded tools. Prices per 1M tokens from platform.kimi.ai/docs/pricing/chat.md read 2026-09-02: cache-miss input $3.00, cache-hit input $0.30, output $15.00. Context window 1,048,576 tokens stated in the same table. Release date, knowledge cutoff and max output tokens are not published by Moonshot (null, not zero). Moonshot names K3 as the migration target for every deprecated and retired model in its catalog. Moonshot consolidated its three per-model pricing pages into one table on or before 2026-09-11: chat-k3.md, chat-k26.md and chat-k27-code.md now all 307-redirect (temporary, per the header) to /docs/pricing/chat.md, which restates these exact rates and context window unchanged. Citation repointed there; our own link maintenance, not a provider price change, so no changelog event.
Kimi K3 by Moonshot costs $3 per 1M input tokens and $15 per 1M output tokens ($6/1M blended), with a 1.0M (1.048.576-token) context window. It is generally available (GA).
Last verified: 26 Sep 2026 · sourced from official provider documentation
◎ You're on the watch list. We'll ping you the moment a model launches, changes price, or gets deprecated.
✕ Couldn't subscribe right now — please try again in a moment.
Free forever · no spam · unsubscribe anytime.
Kimi K3 — questions & answers
How much does Kimi K3 cost?
Kimi K3 is priced at $3 per 1M input tokens and $15 per 1M output tokens ($6/1M blended at a 3:1 input-to-output ratio), with cached input at $0.3 per 1M tokens.
What is the context window of Kimi K3?
Kimi K3 has a 1.048.576-token context window (1.0M).
Is Kimi K3 deprecated?
No — Kimi K3 is generally available (GA) and not currently scheduled for deprecation or retirement in our tracker.
Does Kimi K3 support image or vision input?
Yes — Kimi K3 accepts image input. Listed modalities: text, image.
Can I self-host Kimi K3?
No — Kimi K3 is proprietary. Its weights are not publicly released, so it is available only through Moonshot's API (or hosted partners), not for self-hosting.
What is the API model string for Kimi K3?
The API model identifier for Kimi K3 is "kimi-k3" when calling Moonshot's API.
Track Kimi K3 price & status changes
New models, price cuts, and deprecations — a short email when something actually changes. No spam, unsubscribe anytime.
The last few changes we caught — this is what lands in your inbox:
- DeprecatingGoogle re-pointed the Gemini 2.5 TTS migration path past the 3.1 preview and onto the new GA 3.8 TTS models
- New modelGemini 3.8 Flash TTS is GA - a flagship text-to-speech model at under half the audio rate of the preview it replaces, on a two-column price schedule
- New modelGemini 3.8 Flash-Lite TTS is GA - Google's cost-efficient TTS, which Google says was built to replace Gemini 3.1 Flash TTS
◎ You're on the watch list. We'll ping you the moment a model launches, changes price, or gets deprecated.
✕ Couldn't subscribe right now — please try again in a moment.
Free forever · powered by the same data on this page.